© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13157
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequences or repetitions of events and successes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    consecutive occurrences or repetitions of events (e.g., "in a row", "straight", "consecutive").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.59
     Italijanski
    -0.53
    énario
    -0.45
    Diweddarwch
    -0.40
    ########.
    -0.40
    "])){
    -0.38
    ioutil
    -0.36
     الحره
    -0.35
    المكان
    -0.35
     препратки
    -0.35
    POSITIVE LOGITS
     consecutive
    1.95
     consecutively
    1.91
     successive
    1.69
     подряд
    1.66
     successively
    1.59
     consecu
    1.52
    secutive
    1.38
     succession
    1.34
     sequentially
    1.28
     suces
    1.27
    Activations Density 0.286%

    No Known Activations